jppaolim commited on
Commit
d4d5a94
1 Parent(s): 4da2b62

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|Title|>": 50257, "<|Step 4|>": 50261, "<|Step 2|>": 50259, "<|Step 3|>": 50260, "<|Step 5|>": 50262, "<|Step 1|>": 50258}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "additional_special_tokens": ["<|Title|>", "<|Step 1|>", "<|Step 2|>", "<|Step 3|>", "<|Step 4|>", "<|Step 5|>"]}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./Model_Base/gpt2-large/ResizedAvg/", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff